Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Security codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genetically
    -0.06
     Eve
    -0.06
    ("-");↵
    -0.06
    Eta
    -0.06
    him
    -0.06
    xit
    -0.06
     หาก
    -0.06
    ery
    -0.06
     Mand
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
     precinct
    0.08
     fundraising
    0.07
    lang
    0.06
    Published
    0.06
     Prof
    0.06
    AIL
    0.06
     Consequently
    0.06
    artment
    0.06
    roduce
    0.06
     бар
    0.06
    Act Density 0.031%

    No Known Activations